Control Your PC with Gemini AI

A modern, modular application for controlling your computer using natural language commands powered by Google's Gemini AI technology.

download Get Started description Documentation
Gemini PC Control Demonstration

Key Features

language

Natural Language Control

Control your PC with everyday language instead of complicated commands.

auto_awesome

Gemini AI Powered

Leverages Google's latest Gemini AI models for intelligent context understanding.

extension

Plugin Extensibility

Extend functionality with custom plugins to meet your specific needs.

devices

Cross-Platform

Works seamlessly on Windows, macOS, and Linux operating systems.

computer

Modern UI

Clean PyQt6-based user interface with intuitive controls.

shield

Local Processing

Your commands are processed locally for improved privacy and security.

Architecture Overview

Gemini PC Control features a modern, modular architecture designed for maintainability, extensibility, and performance.

  • UI Module: Modern PyQt6 interface with proper separation from business logic
  • AI Module: Enhanced Gemini API integration with context tracking
  • System Module: Core system operations (screenshots, command execution)
  • Models: Structured data models for commands and responses
  • Plugins: Extensible plugin system for custom functionality
Gemini PC Control Architecture Diagram

Installation

Quick Automated Setup

Run the automated setup script to handle everything:

git clone https://github.com/yourusername/gemini-pc-control.git
cd gemini-pc-control
python setup.py setup_env

This will:

  • check Create a virtual environment
  • check Install all dependencies
  • check Prompt for your Gemini API key
  • check Create a run script

Manual Installation

For more control, follow these steps:

1. Clone the repository:

git clone https://github.com/yourusername/gemini-pc-control.git
cd gemini-pc-control

2. Create a virtual environment:

# Using venv (recommended)
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

4. Run the application:

python app.py

System Requirements

Basic Requirements:

  • Python 3.11 or higher
  • Google Gemini API key

Debian/Ubuntu Dependencies:

sudo apt-get update
sudo apt-get install -y python3-dev python3-venv
sudo apt-get install -y qt6-base-dev libqt6-dev
sudo apt-get install -y build-essential libssl-dev libffi-dev

macOS Dependencies:

brew install qt@6
export PATH="/opt/homebrew/opt/qt@6/bin:$PATH"

Windows Dependencies:

  • Microsoft Visual C++ Build Tools
  • Qt6 (Download from qt.io)

Documentation

play_arrow

Getting Started

Learn how to set up and run Gemini PC Control for the first time.

Read More
code

API Reference

Detailed documentation of the application's modules and classes.

Read More
extension

Plugin Development

Create custom plugins to extend the application's functionality.

Read More
help_outline

Troubleshooting

Solutions to common issues and frequently asked questions.

Read More